Best Practices for Road Weather Management Version 2.0
A Cross-Correlation Tracking Technique for Extracting Speed from Cameras Under Adverse Conditions
This paper presents an algorithm to estimate speed from traffic surveillance cameras in a variety of traffic congestion, weather, and lighting conditions. The features from the images are projected into a one-dimensional subspace and transformed into a linear coordinate system using a simplified camera model. A cross-correlation technique is used to summarize the movement of features through a group of images and to estimate mean speed for each lane of vehicles. A Kalman filter technique using a set of maximum likelihood optimal parameters is used to estimate the traffic speed by lane to create an optimal space-averaged speed.
83rd Transportation Research Board (TRB) Annual Meeting, University of Washington. For an electronic copy of this resource, please direct your request to WeatherFeedback@dot.gov.
Closed Circuit Television (CCTV)
PDF files can be viewed with the Acrobat® Reader®.